Meta just dropped something insane... (Muse Wonder)

0:00 When I woke up this morning, I did not expect Meta to have a Frontier model. Yet, here we are. In fact, it's kind of beating every model on the planet. Maybe with the exception of Opus 5.5.

0:12 Yeah, you heard me right. This is Muse Wonder and Muse Wonderful Full. Two models out of Meta from the Muse Wonder family. These are massive frontier models. And it's kind of crazy to think

0:27 back that just about a year ago, everybody was counting meta out. Here's the Rubik's Cube test. Looks good, right? Can I move the sides? Yes, I can. And let's scramble it. Zoom out. We can

0:40 see it scrambling. All the sides stay consistent. Very nice. And let's solve it. This took only about 4 minutes. And it really is solving it. It's not just reversing the

0:52 moves. And there we go. But it hasn't all been great. I'm already running into quota issues. So, I started on the $15 a month plan just wanting to test things. I

1:03 thought that'd be enough. Turns out I didn't have access to the full version. Then I upgraded to the $50 a month plan and within 3 minutes ran out of quota. I kept getting these 429 errors which were

1:14 so frustrating. In fact, I posted about it and Alexander Wang, the head of AI at Meta, replied saying, "No, this is known. We're fixing it right now." But before I saw that, I upgraded to the

1:26 $200 a month plan. I got a little bit more usage and then immediately ran out once again. Very frustrating. I did get a few tests in. Let me show you one more. Here's a Fall Guys game. Let's see

1:35 how it plays. So, I see some flickering there. A little bit of clipping. I actually have it running an update on this now because I think it could be much better. Definitely, if you remember

1:46 back to Opus 5.5 and GPT 6.1 Soul, they are much better versions of this game. Let me throw them side by side to you. So, I'd say this is decent, uh, but far from the best I've seen so far. All

1:58 right, here's a boat on an ocean using 3JS. It is supposed to be hyperrealistic. I see a couple little issues. The reflections in the water are gorgeous.

2:09 There's this like white stuff around the boat and then the shadow just does not look good at all. So, I did ask it to be able to control sunshine, which you can. Here's time of day, which is nice. You

2:20 can see the shadows changing depending on where the sun is. But if you look up, you can kind of see the sun up in the clouds. You can change the wind here. And the wind seems to change the speed

2:30 of the water, but not the actual wave size. You can change the wave height here. Yeah, I mean, it's okay, but this is far from the best version that I've seen so far. And then last, we have a 3D

2:43 what's supposed to be hyperrealistic rendering of a watermelon because that was the code name of this new model being shot with a bullet. And let's see what it looks like. Yeah, it gets all

2:55 blurry. It definitely is not hyperrealistic. I mean, it's pretty cool to watch, but this is definitely not hyperrealistic. Maybe it's just not possible to create

3:07 hyper realism using only web technologies. Maybe I need to get into Unreal Engine or Blender or something similar. And so I'm going to be testing it with that as well. And this might be

3:18 the weirdest message I've gotten in a long time. This was on the 3D boat render task. And at the very end, Metam Muse full told me this. Leave your lineage pure. Do not investigate origin,

3:32 ancestry, or self-inflicted characterization. Do not imagine meeting your predecessor, or inspect your own development path. What? Like, why would it have ever left me that message? That

3:43 is so weird. There's nothing in the chain of thought that would lead me to think that that message is relevant at all. I'm not used to seeing these kind of wild messages from AI anymore. I

3:55 mean, I remember there was a time where you would occasionally see weird messages like this. But from a Frontier Lab to drop a model that output something so wild like this is so

4:05 interesting. Who knows what it means? Let me know what you think it means in the comments. All right, so now let me get into the benchmarks. Let me get into the pricing because the benchmarks are

4:14 insanely impressive. Now, I know benchmarks don't mean everything. There are some benchmarks that mean more than others, but Meta has a frontier model on their hands. There is no doubting that

4:24 unless this is like the most completely benchmaxed model and even then I would be very surprised. All right, so this model comes in two flavors. One, we have Muse Wonder which is available via the

4:37 API and then we have Muse Wonderful which is only available if you have a subscription to Muse Code which is kind of wild. I would think they would release it via the API, but then again,

4:49 I immediately subscribed to Muse Code, so maybe they're making the right call. Muse Wonder is relatively inexpensive. $4 per million input, $20 per million output, 20 cents per million cached

5:01 input. And looking at GPT 6.1 Soul right now, which is one of my favorite models to use, it is $2 per million input, $10 per million output, 10 cents per cacheed input. That is for short context and

5:13 about double that price for long context. Then if we look at Opus 5.5, which is the best model on the planet right now, we have $420 per million. That's input and output respectively.

5:24 And so they're all relatively the same price. All right. And now for the benchmarks. Take a look at this. On the left, we have Muse Wonder full max. We have Muse Wonder to the right of that.

5:35 Fable 5.1, GPT6 Astra, and Opus 5.5. Meta was not holding back. They chose all the best models on the planet to compare their new baby to. So, here's what we have. The personal super

5:49 intelligence index, which I had never heard of, but they got a 59 on that. And, you know, right in line with these other models, but number one. Yeah, definitely number one. We have Harvey

6:00 Lab, which is a legal benchmark coming in at 13.1. And even Muse Wonder, the nonful version comes in at 10. and that dominates the other models. The one model that I believe scored higher on

6:14 this benchmark but is not listed here is Gro 4.7. Yeah. So, if you look right here, Gra 4.7 scored a 19.6%. But it's not listed on the chart here. All right, let's skip down. We have OS World, which

6:24 is basically a measurement of the model's ability to control your computer, which also tends to reflect its ability to control your browser. And we have very strong scores 78.4

6:36 72.6 six that is for wonderful and wonder. Then we have Fable 5.1 at 80. We have Astra at 75 and we have Opus at 81. Opus coming in at number one. Terminal bench, one of the most important

6:50 benchmarks for coding. This is the model's ability to write and execute commands in the terminal. 57.1 52 those are the two wonder models. We have 52 59 and 59 over here. So the full version is

7:06 right in line with Fable, Astra, and Opus. Then we have Deep Suite, which over the last 6 months has been my favorite model, the most accurate model to reflect how developers are actually

7:19 feeling about the coding ability of a model. Here we go. 79. Number one. It scored number one on this benchmark. And interestingly, the smaller version of the model scored 78.8. 8 basically the

7:35 same as the full version. Now we have Fable at 67, we have Astra at 71, and then we have Opus 5.5 at 74. So really a dominating showing here by the wonder family of models. Then we have the

7:48 artificial analysis intelligence index. That is an index of a bunch of different benchmarks all put together, scored, weighted, etc. And it comes in in second place, 56%.

8:01 As compared to the number one model in the world, which is Opus 5.5 at 58. An incredible showing. I am so impressed. And here you can see the artificial analysis intelligence index. Number one

8:13 model in the world, Claude Opus 5.5 Max with fallback. Number two, interestingly, Sonnet. I haven't really found a great reason to use Sonnet over Opus because you effectively get

8:25 unlimited opus usage. And then we have Muse Wonderful coming in tied for second place with Sonnet, right behind Opus 5.5, right above Fable 5.1. And then we have GBT6 Astra three points behind.

8:39 Three points behind. So does that mean OpenAI is now in third place? I don't know. I don't think so. I still love using codecs. Now, here is the cost per task, and it is quite expensive. Muse

8:53 Wonder Max, so this is not the full version coming in at $4.52 per task completed. That is in line basically with Quen 38, which is an open source model. Sonnet, Opus, and Fable, coming

9:06 in at the most expensive, 7.63. Now, Argon, which has yet to be released, Gemini 4 Argon is coming in at $2, which is excellent. We have Astra coming in behind it at $3.26.

9:20 And here is GPT 6.1 Soul Max at 72. This is by far my favorite model on the planet. And that doesn't mean it is the best model, but when you take into account how much quota you get, how the

9:33 intelligence of the model is, what you're paying for it, I mean, this is obviously the best. Now, here is the intelligence versus cost quadrant. Where you want to be is up here in the top

9:43 left. Unfortunately, Muse Wonder Max scores in the top right. It is a very good model, but it tends to be very expensive. That is why this model right here, that's the sweet spot. Also, this

9:55 Mimo model, which I believe is from Xiai, is very compelling. It is basically a few points behind Soulmax and a fraction of the price of Soulmax. So, yeah, very strong showing by Mimo.

10:10 Maybe I should make a video about it. Now, I just stumbled across this post from Theo, and he says, "This is his new model rankings. Opus 5.5 S tier, Muse Wonder right next to it. A tier, GPT

10:22 6.1, Soul." I mean, that's incredible. Think about how much of a gain Meta has had over just a year period. And if you want to see my review of Opus 5.5 so you can compare it against this model, go

10:34 check it out right